Blog
Learn how to prepare work for AI coding agents and evaluate the result. Halvic Labs GmbH explains specifications, task planning and review using Anvil Coder, with practical examples and explicit limitations.
These articles are published by the product developer, not an independent review body. Illustrative examples are labelled; the documented reference run separately records its results and verification limits.
2026-09-02
Spec-driven development with Anvil Coder: from a specification through tickets and commits to a draft pull request, with checks and human review.
2026-09-02
How Anvil Coder turns project rules into prompt instructions and executable checks, and why an instruction alone does not prove compliance.
2026-08-26
How Anvil Coder splits epics from YouTrack, Jira, GitHub and GitLab into stories, using configured triggers, separate coding approval and model usage.
2026-08-17
Spec-driven development uses a versioned specification as the working reference. Connect requirements, acceptance criteria, planning and code review.
2026-08-10
Separate approvals during AI coding from final code acceptance. Understand project settings, verification logs and human review before merging.
2026-08-03
Commits make changes traceable but do not prove that tests passed. Connect diffs, requirements and verification logs when reviewing AI-generated code.
2026-07-27
Put architecture rules in an AI agent's working context and support them with checks. Learn how to express constraints, examples and verification limits.
2026-07-20
Small TaskSlices bound the context and simplify review. Learn which tasks can be separated and why integration tests and dependency planning still matter.
2026-07-13
Prepare Anvil Coder with access, a repository, project rules and a small first ticket. Understand usage costs, verification and the final review.